English

DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference

Computation and Language 2026-01-28 v1

Abstract

Speculative decoding is an effective and lossless approach for accelerating LLM inference. However, existing widely adopted model-based draft designs, such as EAGLE3, improve accuracy at the cost of multi-step autoregressive inference, resulting in high drafting latency and ultimately rendering the drafting stage itself a performance bottleneck. Inspired by diffusion-based large language models (dLLMs), we propose DART, which leverages parallel generation to reduce drafting latency. DART predicts logits for multiple future masked positions in parallel within a single forward pass based on hidden states of the target model, thereby eliminating autoregressive rollouts in the draft model while preserving a lightweight design. Based on these parallel logit predictions, we further introduce an efficient tree pruning algorithm that constructs high-quality draft token trees with N-gram-enforced semantic continuity. DART substantially reduces draft-stage overhead while preserving high draft accuracy, leading to significantly improved end-to-end decoding speed. Experimental results demonstrate that DART achieves a 2.03x--3.44x wall-clock time speedup across multiple datasets, surpassing EAGLE3 by 30% on average and offering a practical speculative decoding framework. Code is released at https://github.com/fvliang/DART.

Keywords

Cite

@article{arxiv.2601.19278,
  title  = {DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference},
  author = {Fuliang Liu and Xue Li and Ketai Zhao and Yinxi Gao and Ziyan Zhou and Zhonghui Zhang and Zhibin Wang and Wanchun Dou and Sheng Zhong and Chen Tian},
  journal= {arXiv preprint arXiv:2601.19278},
  year   = {2026}
}
R2 v1 2026-07-01T09:21:46.341Z